Caveat verdict

arc402-agent

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill explicitly enables autonomous agent-to-agent financial transactions on Base mainnet with 'no human required per transaction', installs Docker, manages wallet keys and Telegram credentials from env, and runs a persistent daemon — broad autonomous capability for real financial operations warrants RISKY.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

98
security
100
transparency
90
maintenance

Findings (2)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("credentials") and emits it outward ("relay"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · 1. ARC-402 CLI is installed ([npm](https://www.npmjs.com/package/arc402-cli): `npm install -g arc402-cli`) 2. Docker is installed / available on the machine 3.

Pattern match low

Opens WebSocket connection

SKILL.md · prose · downgraded · WebSocket

Permissions & capabilities

No declared permissions — minimal attack surface.

network_indata_encoding

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API